← All models
Flash — fastest and cheapest, lighter reasoningOpen Weights
Hy-MT2-1.8B Pricing
Tencent · tencent-hy-mt2-1-8b
Input / 1M tokens
$0.044
Output / 1M tokens
$0.177
Context window
8,192 tokens
Max output
4,096 tokens
What it costs in practice
Typical request (1,200 in + 400 out tokens)$0.0001
1,000 requests / month$0.1236/mo10,000 requests / month$1.24/mo100,000 requests / month$12.36/moEstimate your own workloadOpens the calculator with Hy-MT2-1.8B preloaded — adjust volume and token counts there.
Price history
Only one price point recorded so far.
The staircase chart appears once a price change is detected.
What it excels at
Efficient for high-volume, low-complexity text tasks such as classification, extraction, or simple generation at low latency.
The business tradeoff
Small parameter count restricts reasoning depth and factual reliability; output token pricing is relatively high for its capability tier.
Head-to-head
Vendor list rates, as of Aug 20, 2026 · source: openrouter · per-request examples assume 1,200 input + 400 output tokens.